skills.rest
xiaotianfotosxiaotianfotosCommunity·4 Agent Skills Included

skills

Create narrated math videos, control TVs, and analyze media with AI

Generates narrated math teaching videos from problem photos using Manim animations, TTS voiceover, and storyboard scripts. Controls DLNA TVs and speakers, runs Claude Code in background tmux sessions, and analyzes videos or images with multimodal AI. Removes manual video editing, device setup, and log tracking so agents complete media and teaching workflows end to end.
580|161
↗
npx skills add xiaotianfotos/skills --all -g -y

All Skills in This Repository (4)

Pure Emerald Level Indicators
📦 In Repo
xiaotianfotosxiaotianfotos

video-understand

Analyze video content with a multi-modal Omni model via OpenRouter API.

Community
Advanced
📦 In Repo
xiaotianfotosxiaotianfotos

claude-in-tmux

Manage Claude Code CLI in tmux sessions for background tasks and logging.

Community
Intermediate
📦 In Repo
xiaotianfotosxiaotianfotos

dlna

Automate media playback on DLNA/UPnP devices via network discovery and control commands.

Community
Intermediate
📦 In Repo
xiaotianfotosxiaotianfotos

tutor

Generate narrated Manim math tutorial videos from geometry problems through an eight-step workflow.

Community
Advanced

Frequently Asked Questions

FAQPage Schema
How to install xiaotianfotos skills?▼

Run `npx skills add xiaotianfotos/skills --all -g -y` in your terminal to install all skills in this suite globally.

How to make a math teaching video with AI?▼

The tutor skill turns a math problem into a full pipeline: analysis, HTML visualization, storyboard, TTS voiceover, and a rendered Manim animation video.

Can AI play videos on my smart TV?▼

Yes. The dlna skill discovers DLNA devices on your network and plays media URLs on TVs and speakers with simple commands.

How to run Claude Code in the background?▼

The claude-in-tmux skill runs Claude Code inside tmux sessions with automatic logging, so long coding tasks run in the background.

Can AI understand video and image content?▼

Yes. The video-understand skill sends videos and images to a multimodal model to generate descriptions, transcripts, and recreation prompts.

Related Repositories in Education & Research

View All in Education & Research→
shareAI-labshareAI-lab
75.8k

learn-claude-code

Learn to build AI agent harnesses from scratch

Official📦 4 Skills
microsoftmicrosoft
73.6k

ai-agents-for-beginners

Learn to build, deploy, and secure AI agents step by step

Official📦 8 Skills
leonardomsoleonardomso
66.5k

33-js-concepts

Master 33 essential JavaScript concepts with tested, verified guides

Community📦 6 Skills